About this Course

100,169 recent views

Learner Career Outcomes

37%

started a new career after completing these courses

38%

got a tangible career benefit from this course
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
Flexible deadlines
Reset deadlines in accordance to your schedule.
Approx. 17 hours to complete
English

Skills you will gain

Data Clustering AlgorithmsK-Means ClusteringMachine LearningK-D Tree

Learner Career Outcomes

37%

started a new career after completing these courses

38%

got a tangible career benefit from this course
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
Flexible deadlines
Reset deadlines in accordance to your schedule.
Approx. 17 hours to complete
English

Offered by

Placeholder

University of Washington

Syllabus - What you will learn from this course

Content RatingThumbs Up91%(5,747 ratings)Info
Week
1

Week 1

1 hour to complete

Welcome

1 hour to complete
4 videos (Total 25 min), 4 readings
4 videos
Course overview3m
Module-by-module topics covered8m
Assumed background6m
4 readings
Important Update regarding the Machine Learning Specialization10m
Slides presented in this module10m
Software tools you'll need for this course10m
A big week ahead!10m
Week
2

Week 2

5 hours to complete

Nearest Neighbor Search

5 hours to complete
22 videos (Total 137 min), 4 readings, 5 quizzes
22 videos
1-NN algorithm2m
k-NN algorithm6m
Document representation5m
Distance metrics: Euclidean and scaled Euclidean6m
Writing (scaled) Euclidean distance using (weighted) inner products4m
Distance metrics: Cosine similarity9m
To normalize or not and other distance considerations6m
Complexity of brute force search1m
KD-tree representation9m
NN search with KD-trees7m
Complexity of NN search with KD-trees5m
Visualizing scaling behavior of KD-trees4m
Approximate k-NN search using KD-trees7m
Limitations of KD-trees3m
LSH as an alternative to KD-trees4m
Using random lines to partition points5m
Defining more bins3m
Searching neighboring bins8m
LSH in higher dimensions4m
(OPTIONAL) Improving efficiency through multiple tables22m
A brief recap2m
4 readings
Slides presented in this module10m
Choosing features and metrics for nearest neighbor search10m
(OPTIONAL) A worked-out example for KD-trees10m
Implementing Locality Sensitive Hashing from scratch10m
5 practice exercises
Representations and metrics30m
Choosing features and metrics for nearest neighbor search30m
KD-trees30m
Locality Sensitive Hashing30m
Implementing Locality Sensitive Hashing from scratch30m
Week
3

Week 3

3 hours to complete

Clustering with k-means

3 hours to complete
13 videos (Total 79 min), 2 readings, 3 quizzes
13 videos
An unsupervised task6m
Hope for unsupervised learning, and some challenge cases4m
The k-means algorithm7m
k-means as coordinate descent6m
Smart initialization via k-means++4m
Assessing the quality and choosing the number of clusters9m
Motivating MapReduce8m
The general MapReduce abstraction5m
MapReduce execution overview and combiners6m
MapReduce for k-means7m
Other applications of clustering7m
A brief recap1m
2 readings
Slides presented in this module10m
Clustering text data with k-means10m
3 practice exercises
k-means30m
Clustering text data with K-means16m
MapReduce for k-means30m
Week
4

Week 4

4 hours to complete

Mixture Models

4 hours to complete
15 videos (Total 91 min), 4 readings, 3 quizzes
15 videos
Aggregating over unknown classes in an image dataset6m
Univariate Gaussian distributions2m
Bivariate and multivariate Gaussians7m
Mixture of Gaussians6m
Interpreting the mixture of Gaussian terms5m
Scaling mixtures of Gaussians for document clustering5m
Computing soft assignments from known cluster parameters7m
(OPTIONAL) Responsibilities as Bayes' rule5m
Estimating cluster parameters from known cluster assignments6m
Estimating cluster parameters from soft assignments8m
EM iterates in equations and pictures6m
Convergence, initialization, and overfitting of EM9m
Relationship to k-means3m
A brief recap1m
4 readings
Slides presented in this module10m
(OPTIONAL) A worked-out example for EM10m
Implementing EM for Gaussian mixtures10m
Clustering text data with Gaussian mixtures10m
3 practice exercises
EM for Gaussian mixtures30m
Implementing EM for Gaussian mixtures30m
Clustering text data with Gaussian mixtures30m

Reviews

TOP REVIEWS FROM MACHINE LEARNING: CLUSTERING & RETRIEVAL

View all reviews

About the Machine Learning Specialization

Machine Learning

Frequently Asked Questions

More questions? Visit the Learner Help Center.